{"ID":2827083,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17541","arxiv_id":"2512.17541","title":"FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation","abstract":"We present FLEG, a feed-forward network that reconstructs language-embedded 3D Gaussians from arbitrary views. Previous feed-forward language-embedded Gaussian reconstruction methods are restricted to a fixed number of input views and typically attach a language-aligned semantic embedding to each Gaussian, resulting in impractical input settings and semantic redundancy. In contrast, we introduce a geometry-semantic dual-branch distillation framework that enables flexible input from arbitrary multi-view images without camera parameters. We also propose a novel-view-based distillation strategy during training that mitigates overfitting to input views. In addition, we observe that semantic representations are significantly sparser than geometric ones, and per-Gaussian language embedding is unnecessary. To exploit this sparsity, we design a decoupled language embedding strategy that represents language information with a sparse set of semantic Gaussians, rather than attaching embeddings to every Gaussian. Compared with dense pixel-aligned per-Gaussian embedding schemes, our method uses only 5\\% of the language embeddings while maintaining comparable semantic fidelity, effectively reducing storage costs. Extensive experiments demonstrate that FLEG outperforms state-of-the-art feed-forward reconstruction and language-embedded Gaussian methods in both reconstruction quality and language-aligned semantic representation. Project page: https://fangzhou2000.github.io/projects/fleg.","short_abstract":"We present FLEG, a feed-forward network that reconstructs language-embedded 3D Gaussians from arbitrary views. Previous feed-forward language-embedded Gaussian reconstruction methods are restricted to a fixed number of input views and typically attach a language-aligned semantic embedding to each Gaussian, resulting in...","url_abs":"https://arxiv.org/abs/2512.17541","url_pdf":"https://arxiv.org/pdf/2512.17541v2","authors":"[\"Qijian Tian\",\"Xin Tan\",\"Jiayu Ying\",\"Xuhong Wang\",\"Yuan Xie\",\"Lizhuang Ma\"]","published":"2025-12-19T13:04:13Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}